click to visit StorageSearch.com home page
leading the way to the new storage frontier .....
SSDs over 163  current & past oems profiled
SSD news ..
pcie  SSDs - click to read article
PCIe SSDs ..
Rackmount SSDs click for news and directory
rackmount SSDs ..
RAM image - click for RAM directory, articles and news
RAM ..
image shows megabyte waving the winners trophy - there are over 200 SSD oems - which ones matter? - click to read article
top SSD companies ..
hybrid DIMMs
hybrid DIMMs ..
.....
SSD ad - click for more info
.....
Micron logo - click for more info

Micron Technology

Micron Technology, Inc., is one of the world's leading providers of advanced semiconductor solutions. Through its worldwide operations, Micron manufactures and markets DRAM, NAND flash memory, CMOS image sensors, other semiconductor components, and memory modules for use in leading-edge computing, consumer, networking, and mobile products.

see also:- Micron - mentions on StorageSearch.com and Micron's SSD page

SAS SSDs
PCIe SSDs
2.5" PCIe NVMe SSDs
RAM ain't what it used to be
hostage to the fortunes of SSD
after AFAs - what's the next box?
are we ready for infinitely faster RAM? (and what would it be worth)
..
If you're one of those who has suffered from the memory shortages it may seem unfair that despite their miscalculations and over optimimism the very companies which caused the shortages of memory and higher prices - the major manufacturers of nand flash and DRAM - have been among the greatest beneficiaries.
miscellaneous consequences of the 2017 memory shortages
..
Micron - and the big picture of the memory market

by Zsolt Kerekes, editor - StorageSearch.com - April 6, 2017

One of the prevailing market forces affecting all memory makers right now is that there isn't enough manufacturing capacity to fulfill all needs.

This situation clarified with prices rising in the 2nd half of 2016.

"Not since 2000, have the memory suppliers been in an undersupply situation" said Alan Niebel , CEO - Web-Feet Research - whose company publishes longtitudinal market share data for the memory market.

The causes are complex but partly related to a prolonged cautionary approach by memory makers with respect to investment to stave off the classic cycle of memory boom bust.

Changes in memory cell technology have also played their part in leading to the current shortage of fab capacity.

In recent years memory makers knew that there were big technology changes taking place in the design of DRAM and flash (the move to 3D) and in the flash market - the simultaneous transition to TLC. Until the manufacturability of the new devices could be proven and until the market receptiveness for them was established it just didn't make sense to rush headlong into unquantifiable commitments.

"Industry productivity is still low due to a condition that could be called planar overhang" said William Tidwell, Semiconductor Analyst in his blog Shootout At Yokkaichi - the NAND Industry at the Crossroads on Seeking Alpha. "Planar overhang - being the amount of planar capacity that must be converted as fast as possible to 3D, so the company can take advantage of the denser 3D process. Unfortunately, this conversion process from planar to 3D is basically like buying a house that has to be completely renovated and then finding out that load-bearing walls are involved - and the foundation has to be reinforced."

The established wisdom is that the cure to memory manufacturing capacity problems costs many billions of dollars and the investment risks are always high because memory makers have to guess the product mix from their customers. This used to be easier in the pre SSD era.

Now the cloud companies are the leading edge computer designers (rather than the old time computer box shifters) and the scale of disruptive change in memory design architecture and customer usage patterns make forecasting the worldwide memory mix harder than ever before.

Not everyone agrees that it will take billions of dollars to increase memory fab capacity.

For example in the DRAM market - BeSang argues that 3D Super-DRAM could fix he multi-billion dollar money pit of memory industry's fab capacity roadmap and produce 4x as many die per wafer for around $50 million.

And the memory shortage (and price hikes) will encourage systems designers to look again at memory utilization at a systems level.

Software and controller techniques which incrementally do more work with less memory, or which do the same job with cheaper memory are now more rewarding to investigate and apply. The cloud infrastructure companies are at the leading edge of this. Because every nuanced 15% or 20% of more virtual service delivery goes straight to the bottom line. Whereas in traditional user sites such small differences are below the threshold of triggering design or supplier changes.

And another reason why there doesn't seem to be enough memory fab capacity is that the traditional market gaming has been made more uncertain by the impact of the China market.

"...the multinationals can only produce a tiny percentage of China's memory needs, prompting the government to jumpstart its own 3D NAND and DRAM efforts" said Mark LaPedus in his blog - China Unveils Memory Plans.

And those weren't enough reasons to wait and see how the simultaneous equations of memory fab capacity, device technology costs, market mix on the demand side, and revolutionary changes in future memory systems architecture were likely to get solved - yet another factor for Micron to play the waiting game is that it has traditionally been a buyer of ready made semiconductor fabs by acquiring them from distressed companies.

Since the end of 2016 the memory industry has been waiting for clarification about the spinoff of Toshiba's memory and storage business units.

There has been much speculation written about this.

In a recent article - HDD Implications of Toshiba Memory Unit Sale - Tom Coughlin said "All in all, there are reported to be 10 potential bids for this business."

March 2017 was a fertile month for news stories about the memory systems market - and you can see more details and links in there.

Take a look too at the SSD news archive on StorageSearch.com, storage market research companies and VCs in SSDs.
..
SSD ad - click for more info
..
Micron - challenges from the SSD and SCM market

by Zsolt Kerekes, editor - StorageSearch.com - October 18, 2016

Micron was ranked #5 in the Q2 2016 edition of the Top SSD Companies List which is researched and published by StorageSearch.com.

Micron first entered this series of SSD reader search ranked companies in Q1 2010 and its highest rank (so far) was #3 in Q3 2015.

In the context of the DRAM market - a blog of DRAM brands by revenue from DRAMeXchange which was reported in SSD news in February 2016 said that Micron was the 3rd largest supplier of DRAM in Q4 2015.

Micron is one of 20 significant companies which have made product announcements related to the SCM DIMM wars market.

Threats and challenges for Micron from SSD architecture?

10 years ago the big challenge for Micron and other memory companies (discussed in this publication) was how well they would adapt to the SSD market. It was clear before any of these companies had even heard about the SSD market that the SSD market (and SSD systems architecture) would one day become the biggest consumer of memory devices and change the way they had to do business.

The choice for Micron was - be a commodity supplier of memory to SSD companies or move upmarket and become a leading SSD brand.

As you can read in the articles below - Micron's adaptation to SSDs and the enterprise systems market in particular has been underwhelming.

At the heart of this failure has been the lack of commitment to adopting a software and systems oriented business culture coupled with depending too much on Intel to provide market roadmaps (at a time when Intel itself was floundering around having - too late - discovered it was no longer in charge of where the computer market was going.)

Another component of Micron's under response to the SSD market was I think due to doubts that Micron would be able to make such a transition work sustainably. This would be reinforced by seeing what had happened to other companies in the SSD systems market with success in one or two product generations only providing transient market leadership. And looking ahead from now the roadmap to future enterprise SSD consolidation is expected to be littered with even more dead bodies.

Consolation for Micron's failure to own any leading enterprise SSD systems brand (upto 2013 or 2014) was the fact that its DRAM business seemed to be a beneficiary of big memory architectures. But the winds of change were coming there too.

In 2013 the advent of the first crude memory channel flash SSDs suggested that the DRAM market would see threats from flash. (But that market got mired in litigation for 2 years and due to a weak 1st generation product design it didn't set the world on fire.)

In 2014 in an article - Are you ready to rethink RAM? - I collected together evidence suggesting that "the revolution in use-case-aware intelligent flash could cross over into new enterprise DRAM architecture."

In 2015 there was no doubt that DIMM wars would become a hot war with 9 vendors (now 20) announcing product intentions. (This included Micron's desperate seeming prelaunch of 3DXpoint.)

Market researchers predict that in the next 5 years flash based systems with memory architecture will be capable of reducing market demands for DRAM by upto 80% compared to past usage patterns in servers and there are already signs from the controller market that this tiered memory approach will trickle down to other markets too.

So it will not be "business as usual" for DRAM.

This is a challenge which Micron is well aware of and has itself discussed in various public papers and conferences.

All these challenges go back to systems and business defined answers. Because it's not how you make the raw memory which matters any more - it's how well the memory system and the data delivery architecture and the application software can operate together efficiently within a big SSD controller context.

Here are some more articles you may find interesting:-

Can you trust SSD market data?

hostage to the fortunes of SSD

is remanence in persistent memory a new security risk?

an SSD view of semiconductor memory boom-bust business cycles

latency loving reasons for fading out DRAM in the virtual memory slider mix

SSD ad - click for more info


Micron? - from the enterprise SSD perspective

Editor:- June 10, 2015 - here's a summary of how I view Micron from the enterprise SSD perspective. It's based on some conversations with readers in May and early June 2015 re what I thought about Micron's Storage Unit.

In the past few quarters - from my perspective and past conversations with Micron re enterprise SSD - I rated Micron as having a very weak direct understanding of the enterprise SSD systems market and no real strong products apart from standard offerings which are easily substitutable.

From the short term business perspective that weakness makes it less risky for other SSD companies (without fabs) to do business with Micron – because they can judge Micron is not well placed to replace them.

Micron is the only company (among the major memory and HDD companies in the same market) which hasn't acquired any significant enterprise SSD companies in the past 12 to 18 months. For years they didn't understand the enterprise and they still don't have the IP or brands needed. So they should feel strong pressure to do something. But making a big move after years of doing nothing is risky too.

Taken together Micron's enterprise storage strategy has not met the basic needs of Micron as a memory company. It doesn't have any strong SSD architectures and systems roadmaps of its own.

.
Who's who in SSD? - Micron

by Zsolt Kerekes, editor - StorageSearch.com - February 2014

In the quarter ended November 28, 2013 - Micron said that about 50% of its nand flash memory bits went into SSDs.

Micron also reported significant growth in its server RAM business in this quarter.

However, in the next few years I think it's likely that this server DRAM business will be impacted by the growing adoption of server based flash - initially by PCIe SSDs (a market in which Micron itself participates directly) and later to a growing extent by memory channel flash SSDs in the form represented by flash DIMMs from competitor SanDisk.

The general effect of server based flash on server DRAM is to reduce the number of servers required to service like for like apps and users. (SSD-CPU equivalence)

In the past few years, however, the RAM impact of this transition has mostly been to move more RAM into fewer servers.

In the next few years, however, flash SSDs may also begin to replace a proportion of memory capacity which was previously done by DRAM.

Micron doesn't currently have a low latency, high capacity, flash DIMM SSD technology platform in its product line. (Micron's hybrid DIMMs - which are flash backed DRAM DIMMs are entirely different.)

But I think it's inevitable that Micron will - at some stage in 2014 or 2015 - have to publicly address this flash DIMM SSD accelerator product gap / opportunity / threat to maintain confidence in its server customer base.

Possible ways of doing this are:-
  • ammending the Hybrid Memory Cube architecture to support internal flash controllers (a possibility I wrote about back in 2011)
  • licensing or acquiring a similar flash DIMM interface controller technology.
  • developing something similar internally
  • launching patent lawsuits to slow down competitors
Clearing the patent and IP decks in readiness for the above options for that may have been one of the factors in the December 2013 patent deal with Rambus.

In a related conference call - Satish Rishi, CFO - Rambus said "we haven't licensed the entire controller space... besides DRAM, and on that side of the industry, we're looking to have more licensees... ...Today most of our patents do not read on the interfaces for non-volatile memory... But over time, I think that's going to change and we expect that some of the novel technologies in the non-volatile space as the speeds get higher will probably adopt the type of interfaces that the DRAM industry has used. So we have a lot of upside potential." (...read transcript)

My guess is that - Micron will be conflicted about investing too much, too soon in memory channel SSDs for the same reasons that hard drive vendors originally ignored SSDs.

In the present state of the SSD market - Micron may regard the short term market opportunity of memory channel SSD as - being small compared to something they already do (PCIe SSDs) and - in the long term - as damaging to their DRAM revenue if it succeeeds.


re Micron and SSDs - by Zsolt Kerekes, editor - January 2013

Overriding all previous faltering (and sometimes misdirected) steps taken by Micron in the SSD market in recent years - the company's 2 biggest legacy achievements in the SSD market upto now were clearly revealed in 2012. They were:-
  • revealing that 1/3 of Micron's nand flash trade sales go into SSDs.

    From my point of view - having discussed this type of transition with many of the world's leading memory companies years ago when SSDs were under 1% of their customer sales and not even in their business radar - it's hard to state how significant this is.

    Some other ways you can look at it are...

    Current worldwide memory fab capacity can easily support 3x the SSD volume and probably 10x the annual SSD capacity using already started manufacturing processes.

    Owning SSD brands is now an essential part of forward integration for managing a successful memory business.

    Memory businesses will not be able to survive profitably without strongly estalished and tied SSD routes to market.

    That's because customers want SSDs - not memory. And because SSD makers can switch memory suppliers more easily than server and PC makers could switch them - the position of being outside the SSD box as a commodity supplier of memory isn't attractive.

    See also:- Memory Channel Storage SSDs - will the new concept fly?
.


Who's who in SSD? - by Zsolt Kerekes, editor - June 2012

Micron sampled its 1st SSD products in early 2008 and made its first appearance in the Top 20 SSD Companies list in Q3 2010. But the company dropped out of the list again in the most recent edition of the top SSD companies (Q1 2012).

I spoke to Ed Doller, VP of Enterprise SSD Solutions recently to discuss their enterprise SSD products.

I had been following up a chain of SSD contacts within the company - and I was looking forward to finally getting some useful information about their enterprise SSDs.

I started by saying that I was surprised that the information which is publicly available on Micron's enterprise SSD web pages - lacks the essential data that any serious designer would need to know in order to decide whether to shortlist Micron as a possible supplier.

At the time I looked (in May 2012) the PCIe SSD product datasheets - for example - didn't say anything at all about the internal architecture - and they were light on many performance details too. I wondered if I had been looking in the right places. To me Micron's enterprise SSD web pages gave me a message of product intentions rather than products which were in production and had been fully characterized.

It wasn't me. I learned that's just the way they do things.

Ed Doller said that the company doesn't supply the kind of detailed internal architecture information I was asking for unless they are talking directly to a potential customer which they have identified by their sales efforts and even in those cases the prospects (mostly in the top tier of computer oems) would need to sign an NDA first.

I said Micron's approach - witholding even the most basic technical info - showed me that Micron doesn't know how to market enterprise SSDs and that unless Micron changes the way they presented their SSD info online they would miss out on a big chunk of the enterprise market.

I said my readers include the biggest buyers and specifiers of SSDs and that with so many vendors in the enterprise SSD market - the designers tend to shortlist suppliers from what they see online - because they don't have time to talk to everyone or test more than a small number of different products.

Neither Micron nor anyone else can compile a list of who the biggest SSD users are based on traditional sales data. Because there are many companies which will be huge consumers of enterprise SSDs in the online data economy which fall outside the traditional prospects lists. These SSD users will make the first moves to choose their SSD partners - not the other way around.

I said it's a valid business decision to do business the way Micron was doing it. But to my way of thinking marketing enterprise SSDs the same way as commodity memory products - wasn't the way to maximize their business potential.

One of these days I will have to read some blogs about diplomacy. I thought we weren't getting anywhere but Ed Doller did confirm that they have designed their own SSD controller architecture for use in their enterprise SSDs. And to me - it's a safe inference is that they are also in the DSP IP in SSD pack too.

That means Micron is a more significant SSD IP company than you would think simply by looking at the null data content in their SSD web pages.

If you're thinking of designing in Micron's enterprise SSDs - I would say - don't waste too much of your time visiting Micron's web site - because you won't learn anything useful there. They don't have a scalable online process of disseminating the information you need. You'll need to talk to a real person in their SSD business - and then wait weeks or months - depending how busy they are - to talk to a product specialist who can answer the type of detailed technical questions - which real enterprise SSD companies put in their public web pages. (I'm still waiting to get my questions answered - and when I hear I'll let you know.)

But to get the balance right Micron isn't the only semiconductor company which doesn't know how to market systems products. That kind of thinking is built into the DNA of many chip makers.

These antiquated oem component oriented ways of developing business worked well in the past - but the SSD market isn't like the PC or server market. One of the interesting things about the SSD market is how the memory makers, and the traditional storage companies have very different approaches to each other and also to the pure play SSD companies. There's no right and wrong way. It's whatever gets the business to the next level. But if you're selecting an SSD supplier - then these differences in thinking and doing business and risk management can be more important than the exact specs and prices of the products.

Another positive thing about Micron - is thatall the SSD people I spoke to were very enthusiastic about the enterprise SSD market and optimistic about the advantages Micron had in the SSD business - by being part of a memory company.

They were surprised but not at all offended when I said that it was only an advantage if everything worked out right - but that the advantage of not being tied to a particular memory supplier for designers in competing SSD companies was that they could go with whichever memory product looked best at the time.

I think we'll be hearing a lot more from Micron - but other enterprise PCIe SSD makers won't be putting them at the top of their list of competitors to worry about just yet.

For competing SSD suppliers see these directories:- PCIe SSDs, 2.5" SSDs and SATA SSDs.

Micron recently acquired the assets of UK based Virtensys which marketed rackmount SSDs stuffed with Micron's PCIe SSDs with a patented multi-server sharing virtualization interface.

The leading companies in the enterprise acceleration PCIe SSD market which Micron has to compete with are:- Fusion-io, Texas Memory Systems, OCZ and Virident Systems.

And in the next level down are:- STEC and LSI and then another 40 or so other companies. It's a crowded market - but there's a lot to play for.

Micron is also in the consumer SSD market. I told Micron's SSD marketers right at the outset of our talks that I wasn't interested in discussing that aspect of their business because StorageSearch.com isn't a consumer facing SSD site.

...Later:- in an interview with another PCIe SSD company (July 24, 2012) I was asked -

what do I think will happen to the PCIe SSD market?

Will it eventually be dominated by the semiconductor companies? like Micron and Intel - To find out what I said - ...read the article
.
Micron mentions from SSD Market History

In April 2008 - Micron and Nanya Technology announced they were each investing $550 million in cash in a new joint venture.

In November 2008 - Micron demonstrated prototypes of fast PCIe flash SSDs with 800MB/s throughput, and hinted that 1GB/s SSDs could be available soon. The performance itself (for a prototype) is unremarkable - because 3 other oems already ship flash SSDs with similar (or faster) performance as commercial products. Z's Laws - Predicting Future Flash SSD Performance

In February 2009 - Micron announced restructuring plans will reduce employment at their Idaho sites by approximately 500 employees in the near term and as many as 2,000 positions by the end of the company's fiscal year.

InJuly 2009 - IDT announced it was working with Micron to develop a commercial PCIe flash SSD for the server market. Micron had previously tested market reaction by unveiling a prototype PCIe SSD (with 800MB/s R/W speeds) in November 2008.

In December 2009 - Micron announced it is sampling 6Gbps SATA MLC SSDs in 1.8" and 2.5" form factors. Micron's C300 SSD can achieve a read throughput speed of up to 355MB/s and a write throughput up to 215MB/s.

In February 2010 -Micron announced an agreement to acquire privately held Numonyx in an all-stock transaction worth approximately $1.3 billion.

In August 2010 - Micron Technology announced it is sampling the RealSSD P300 - a 200GB 2.5" SATA 3 SLC flash SSD with R/W IOPS of 44,000 and 16,000 respectively.

In June , 2011 - 30 months after pre-announcing its intentions to enter the PCIe SSD accelerator market - Micron today announced it is sampling the first products in a new family which will ship in the 3rd quarter of this year.

The company says its RealSSD P320h drive delivers upto 750K / 341K R/W IOPS, and 3GB/s / 2GB/s R/W throughput. It uses Micron's own 34nm SLC ONFI 2.1 NAND flash and has on-board RAM cache. Micron says it manufactures most of the chips used in the new cards a customized SSD controller.

In October 2011 - Samsung and Micron launched a new industry initiative - the Hybrid Memory Cube Consortium .

In January 2012 - Micron announced it has acquired the assets UK based Virtensys which marketed rackmount SSDs stuffed with Micron's PCIe SSDs and supported by a patented multi-server sharing virtualization interface.

In January 2013 - Micron disclosed that in the past quarter SSDs had become 17% of Micron's nand business and the company estimates that 35% of the nand flash it supplies to trade customers end up in SSDs.

In July 2015 - Intel began unveiling a new future memory technology co-developed with Micron - called 3DXpoint.

In December 2015 - Micron announced a $3.2 billion transaction to complete its 100% share ownership of Inotera Memories.
.
SSD ad - click for more info
.
.

storage search banner

.
Micron samples industry's first QLC SATA SSDs
Editor:- May 21, 2018 - Micron today announced it is sampling the industry's first SSD built on next generation quad-level cell (QLC) NAND technology.

Micron's 5210 ION (2.5" SATA SSD) is intended to replace HDDs in read mostly cloud storage applications and will be available in capacities ranging from 1.92TB to 7.68TB.

Micron notes that the native endurance of the new 64 layer 3D QLC nand at the cell level is 1K P/E cycles. But for very low DWPD applications (under 1 is my guess) Micron indicates that QLC drives provides a more viable underlying technology to compete with and replace 7,200 RPM nearline hard drives than lower density TLC.

(For comparison - Seagate reported that the average capacity of nearline HDD it shipped in the first calendar quarter of 2018 was 6.5TB).

Editor's comments:- While the availability of QLC SSDs provides another hummable tune in the great solid sate storage songbook I think that storage systems users may not exactly leap into the air with unbridled joy at this announcement - coming as it does after 2 years of much higher ASPs for value based SATA SSDs than the market would have expected prior to the shortage fiasco.

And while the technical challenges of making QLC a working technology are awesome (and industry accolades should go to the designers of the memory internal P/E and read circuits and accompanying data integrity framework in the controllers) the battle lines for opening new markets in next generation memory systems are at the other end of the latency spectrum - in the application zone of what is to replace RAM - and how much of it will even resemble RAM to an degree which is recognizable.
..
Micron hints at AI assisted porting of compute intensive models to FPGA-inside memory array accelerators
Editor:- March 30, 2018 - A new blog - Why Memory Matters in Machine Learning for IoT - by Brad Spiers - Principal Solutions Architect, Advanced Storage at Micron reveals significant progress in software tools development which is intended to reduce the time and complexity of porting machine learning models onto in-situ memory accelerators implemented by FPGAs embedded into DRAM arrays. The blog makes specific reference to applications with Micron's PCIe connected Advanced Computing Solutions (pdf) - which provide FGAs integrated with either DDR-3 or HMC and a design, simulation and runtime support tools.

Among other things - Brad Spiers says... "Micron is engaged with machine learning experts, like FWDNXT, to enable seamless transfer of machine learning models onto FPGAs. Models are first created in the normal way, using the same software that data scientists use every dayCaffe, PyTorch or Tensorflow. The models output by these frameworks are then compiled onto FPGAs by FWDNXT's Snowflake compiler." ...read the article

Editor's comments:- creating AI based software productivity tools which could cut many months off the design time to create FPGA based in-situ memory based application accelerators is an extreme case of Memory Defined Software. Such developments could become as significant for startups creating blue sky HPC based knowledge enabling tools as was the availability of microprocessor development systems for the democratization of digital electronics in the 1970s.
.
SSD ad - click for more info
.
Micron's SSDs tough enough for army
Editor:- February 25, 2017 - Micron isn't a name that would sping to mind when thinking about military SSDs. Which is why I found a new applications white paper from Micron interesting.
military storage directory and news
military SSDs

Micron's IT SSDs withstand DRS' Toughest Tests (pdf) describes how DRS (which is a military SSD company) requalified an industrial SSD - M500IT - which had originally been designed for the automotive market so that it could be used in a large Army program. ...read the article (pdf)
..
SSD ad - click for more info
..
"In 2016 4 shining companies - Diablo, Marvell, NVMdurance and Symbolic IO provided significant technology markers for the way ahead for the SSD memory systems ecosystem."
Zsolt Kerekes, editor - StorageSearch.com in his blog - 1 big market lesson and some companies too (December 20, 2016)

..
"I would be the last person to say this isn't a cyclical business because the one thing that suppliers will never be able to control is the demand environment and as you know we're in a very capital-intensive business.

So, once you have the capacity then almost no circumstances will you choose not to produce because you have a very, very high fixed cost structure and so the industry responded appropriately to the weakening PC demand environment and first nobody added capacity, and secondly, we all shifted our output to those more lucrative segments... "
Ernie Maddock, CFO - Micron (January 10, 2017) at Micron Presents at Needham Growth Conference (transcript - by SeekingAlpha.com) - in reply to a question about the cyclical nature of the memory business and similarities to the previous 2014 cycle.

See also:- boom bust cycles in memory markets - any lessons for SSD?

..
Should we set higher expectations?
where are we heading with memory intensive systems?

..
"The improvements in endurance in going from 2-D to 3-D NAND have clearly not been enough for Intel, Micron and WDC to remain with these technologies for SCM."
Andrew Walker, Founder and CEO - Schiltron - in the article - what were the big SSD, storage and memory architecture ideas which emerged and came into sharp focus in 2016?.

..
3D XPoint - walking back the original claims
Editor:- December 6, 2016 - 3D XPoint: a Guide to the Future of SCM - a recent blog on Tom's Hardware keeps alive the ongoing story of this preannounced and over stated technology which was unveiled by Intel and Micron in 2015 as an investor oriented reassuring response to competitive announcements in the DIMM wars market - which pointed towards a much reduced market long term role for conventional server DRAM.

I - like others - stated my doubts about the so-called market readiness hinted at in the early 3DXPoint razzmatazz. And this year those early doubts have been salami sliced by successive analysis as more technical information has emerged or failed to emerge in support of the early bold claims.

This new blog by Paul Alcorn includes a nicely judged narrative and brings the story of the successive pilot show teasers up to date. Among other things Paul says:-

"unfortunately, the two companies recently began walking the performance claims back."

"...the companies have yet to explain, beyond ECC tuning, why the endurance specifications have taken such a drastic plunge."

"The ultimate goal of the next generation of memory is to have the worlds of storage and memories collide permanently, with just one medium emerging for both purposes. 3D XPoint isn't suitable for that role, at least not yet, but it could help lay the groundwork." ...read the article

Editor's comments:- this is what I said here in SSD news - August 2015...

"Much less easy to place within any particular calendar year and to rate for its significance to future SSD history - however - due to its distinctly vaporware-like aspects and stunning lack of technical details - was the stage managed unveiling of a newly branded memory architecture by Intel and Micron - which (like the emperor's new clothes) may or may not become significant for enterprise applications in 2016, or 2017 or 2018 - depending on when we can see it working and depending on what other competitors are doing at that time."

And in June 2016 - I brought reader attention to a thoughtful video - 3D XPoint, reality, opportunity, competition which looked at boundary capabilities of the technology from a competing semiconductor point of view.

..
Micron wraps up funding to buy Inotera
Editor:- October 12, 2016 - Micron's long delayed plan (announced in December 2015) to complete its ownership of Inotera now has an end date in sight - December 6th, 2016.

Inotera announced yesterday Micron Semiconductor Taiwan Co. Ltd. and Inotera signed a syndicated loan agreement of NT$80BN with a group of banks which will enable MST to acquire all of the issued and outstanding common shares of the Inotera for cash.

..
big idea #3 - retiring and retiering enterprise DRAM
What were the big SSD ideas to learn and forget in 2015?

....
FIPS makes for health compliant SSDs
Editor:- July 28, 2016 - A new blog by Micron - discusses FIPS 140-2 validation in its range of SAS SSDs.

click to see directory of SAS SSD companies
SAS SSDs
..
The blog's author - Anne Haggar, Product Marketing Leader, Micron says (among other things)...

"We are finding that U.S. federal agencies arent the only organizations that are interested in the extra security these drives provide. Companies in health care and financial services who face stiff fines for non-compliance and huge risks if they have a data breach are adding FIPS 140-2 compliance to their requirements." ...read the article

See also:- is data remanence in persistent memory a new risk factor?

..
Micron was #1 researched SSD company in 1H July 2015
SSD news (July 16, 2015 )

..
Micron in production with 16nm TLC
Flash Memory
flash & nvm
Editor:- June 2, 2015 - 2 years after sampling its first 16nm nand flash - which was 2D with MLC nodes (2 bits per cell) - Micron today announced it has progressed to the next evolutionary step and is now shipping 16nm (which is still 2D) but is now 3 bits per cell (TLC).

In both cases the products were 16GB memory chips.

Micron says it believes that TLC will account for almost 50% of the total NAND gigabytes shipped in 2015.
....
Micron is a less threatening flash partner for many enterprise SSD companies to work with.
the Top SSD Companies - 2014 Q4
..
What if you could make RAM itself more intelligent and application aware?
Are you ready to rethink enterprise RAM?
....
Micron ships 2DWPD SATA SSDs
Editor:- April 22, 2014 - Micron today announced that it's shipping new SATA SSDs for the enterprise in 1.8" and 2.5" 7mm high form factors.

disk writes per day in enterprise SSDs
DWPD
The M500DC SSDs - based on 20nm MLC NAND, and with capacities upto 800GB are fast-enough 65K / 24K R/W IOPS (4KB) rated at 1 to 3 DWPD for 5 years.

Editor's comments:- the reason that flash memory makers get excited by such mundanely performing SSDs - is that for every terabyte of fast sexy SSD they can sell in the enterprise market there's another 2 to 50 more terabytes of "value" class SSD capacity they can sell too - if they can get the price, power consumption and reliability right (and not over specified).
...
Micron's HMC controller team win design award
Editor:- April 7, 2014 - Micron today announced that one of its design teams has been named "design team of the year" by EE Times and EDN for the design work - done in collaboration with Altera - which led to the industry's first working Hybrid Memory Cube (HMC) controller.
.
"McObject (whose products include in-memory database software) recently published the results of benchmarks using AGIGA Tech's NVDIMM in which they did some unthinkable things which you would never wish to try out for yourself - like rebooting the server while it was running."
SSD software news - October 9, 2013
.
Micron samples 16nm nand
Editor:- July 16, 2013 - Micron today announced it will be in full production of 16nm nand flash (128Gb MLC memory devices) in Q4 this year - and is designing SSDs around this process geometry - to ship in 2014.
.
Micron turns up the heat for adoption of 2.5" PCIe SSDs.
Editor:- May 2, 2013 - Micron announced it's sampling a new model in the hot swappable 2.5" PCIe SSDs market - the P420m has upto 1.4TB MLC capacity and can deliver 750K R IOPS.

What does this mean for other types of enterprise SSD? See the analysis in SSD news.
..
We're #1 in SSD revenue - says Micron
Editor:- March 7, 2013 - Micron sees itself as the biggest SSD company - in terms of revenue, with about 6% market share in enterprise SSD - according to Kipp A. Bedard, VP Investor Relations - at a recent investors conference - transcribed in an article on SeekingAlpha.com

"In terms of SSDs, if we specifically broke out our SSD revenues, we'd probably be the largest SSD public company today. If I had to guess, were probably running on a revenue basis somewhere around 80%, 85% client, 15% to 20% enterprise"

Other interesting observations in this presentation.

"The average smartphone includes 30GB flash."

"We believe the client SSD market is growing about 20% units q-over-q." ...read the article

See also:- Can you trust SSD market data?
..
Micron enters SAS SSD market
Editor:- February 26, 2013 - Micron today became the 19th company to enter the SAS SSD market.

The company today announced production of its new P410m SSD. This is (a 2.5" SSD with R/W speeds upto 410MB/s and 345MB/s respectively and 50K/30K R/W IOPS for the 400GB model which uses 25nm MLC. Endurance is 10 drive fills per day for 5 years.

Editor's comments:- Micron is currently the only company manufacturing both PCIe and SAS compatible enterprise SSDs in the 2.5" form factor.
..
the 2.5" PCIe SSD guide
Aren't all PCIe SSDs very similar?
Does size matter in SSD design?
What do enterprise SSD users want?
sugaring nand flash for the enterprise
an introduction to enterprise SSD silos
How will hard drives fare in an SSD world?
...
what price a terabyte?
Editor:- January 10, 2013 - Micron announced it will ship SATA SSDs with 960GB capacity priced under $600 in this quarter.

See also:- SSD prices timeline and clarification guide
....
1/3 of Micron's nand flash trade sales go into SSDs
Editor:- December 20, 2012 - Micron - today in a conference call - said that SSD shipments had grown 20% compared to the previous quarter.

SSDs are 17% of Micron's nand business and the company estimates that 35% of the nand flash it supplies to trade customers end up in SSDs.

MLC was about 80% to 85% of nand flash wafer production with SLC and TLC making up the rest.
..
adaptive R/W flash care IP for SSDs
What is it? Who does it?
This will be a disruptive transition.
..
Micron sources holdup technology for NVDIMMs
Editor:- November 14, 2012 - Micron has signed an agreement with AgigA Tech to collaborate to develop and offer nonvolatile DIMM (NVDIMM) products using AgigA's PowerGEM (sudden power loss controller and holdup modules).
....
Dell selects Micron's hot-swap 2.5" PCIe SSD
Editor:- March 6, 2012 - Micron today announced that it has developed a 2.5" form factor, hot swappable, PCIe SSD.

The new solution has been selected as a key storage device in Dell's PowerEdge 12th generation servers.

Editor's comments:- this is a natural progression - from the pioneering work last year by SANRAD (the first company to ship front removable PCIe SSDs) and OCZ (the first company to demonstrate 3.5" PCIe SSDs).

In a recent article - are you designing a new PCIe SSD? - I discussed some of the new storage architectural concepts which are being enabled by new PCIe chips from PLX - in the area of fault tolerance and PCIe enabled SANs.
pcie  SSDs - click to read article So there are a lot more changes in the PCIe SSD product pipeline. 2.5" will be an additional form factor for PCIe SSDs - and won't replace the traditional card / module form factor.
..
Micron samples its first real PCIe SSD
Editor:- June 2, 2011 - 30 months after pre-announcing its intentions to enter the PCIe SSD accelerator market - Micron today announced it is sampling the first products in a new family which will ship in the 3rd quarter of this year.

The company says its RealSSD P320h drive delivers upto 750K / 341K R/W IOPS, and 3GB/s / 2GB/s R/W throughput. It uses Micron's own 34nm SLC ONFI 2.1 NAND flash and has on-board RAM cache. Micron says it manufactures most of the chips used in the new cards a customized SSD controller.

Editor's comments:- if it lives up to its promise - this new SSD range from Micron could be among the fastest PCIe SSDs around. From the viewpoint of a semiconductor memory maker - PCIe SSDs are attractive because they have high added value. That's the theory. In practise - to make an enterprise SSD business work you also have to invest a lot in continuing technical design, compatibility testing, customer support and marketing.
pcie  SSDs - click to read article The true test of Micron's new product therefore is not so much what it's like when it ships to users at the end of this year - but whether Micron decides to stay the course 2 to 3 years down the road.

Where are we now with SSD software?
the New Business Case for SSD ASAPs
How fast can your SSD run backwards?
the Problem with Write IOPS - in flash SSDs
Where does all the money go? (inside SSDs)
Data Integrity Challenges in flash SSD Design
How will 2.5 inch PCIe express SSDs change things?
Why can't SSD's true believers agree about architecture?
.
.

STORAGEsearch is published by ACSL